Research Engineer, Safety Oversight, DeepMind

Software Careers; Greater London; Hybrid; GBP 120,000 - 160,000; Full time

Job summary

Google DeepMind in London is seeking a Research Engineer for Safety Oversight to help turn production data into intelligence on AI model safety. You will build large-scale data pipelines and detectors for misbehavior, while advancing cross-context monitoring and signal aggregation across sessions.

Ideal candidates have 3+ years building technical products in generative AI, LLMs, and automated evaluation, with strong collaboration across safety, infrastructure, and data science teams.

Qualifications

• Bachelor’s degree or equivalent practical experience in a relevant field.
• 3 years of experience building and shipping technical products.
• Experience in generative AI and Large Language Models (LLMs).

Responsibilities

• Build classifiers and large-scale data pipelines to detect model misbehavior and misuse end-to-end.
• Research and develop cross-context monitoring systems to detect coordinated harms.
• Collaborate with infrastructure teams and data scientists to scale work and share results.

Skills

generative AI

LLMs

coding agents

data pipelines

automated evaluation

statistical modeling

model activations

chains-of-thought

Education

Bachelor’s degree or equivalent practical experience

Master’s degree or PhD in Engineering/CS or related field

Job description

# Research Engineer, Safety Oversight, DeepMindat Google • London, UKBack to jobs1. Home2. Jobs3. UK4. Research Engineer, Safety Oversight, DeepMind—G## Research Engineer, Safety Oversight, DeepMindGoogle00AI SafetyFull-timeLondon, UKApply Job### Job DescriptionWe aim to turn production data into intelligence on the safety of deployed AI models. Safety Oversight is a new team tasked with using large-scale production traffic and a variety of automated evaluation methods to monitor the safety and alignment of deployed models. Our work will ensure we measure the real-world efficacy of our safety stack—both of in-model safety training and out-of-model safety mitigations to ensure we are effective in our goal of deploying safe models that are used for widespread public benefit. The Safety Oversight team sits within the GenAI safety organization and is accountable for ensuring that when a model safety issue occurs in production, or when a user is misusing our model at scale, we detect and understand it, so the safety risk can be rapidly mitigated. We will collaborate closely with teams working on safety training and evaluation for Gemini and GenMedia models. The Generative AI (GenA)I Safety team operates in a fast-paced, highly collaborative environment. We take the possibility of tangibly dangerous model capabilities seriously as AI advances, and we believe that proactive monitoring and deployment-time oversight are critical for safe AI development. Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority. We are pushing the boundaries across multiple domains. Our global teams offer diverse learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort.ResponsibilitiesBuild classifiers and large-scale data pipelines to detect model misbehavior and misuse end-to-end. Research and develop cross-context monitoring systems to detect coordinated harms, developing novel signal aggregation methods across disparate user sessions to identify large-scale attack vectors. Think critically about novel methods for monitoring using model activations, actions, chains-of-thought and final answers. Collaborate closely with infrastructure teams and data scientists to scale your work and regularly share results with the wider safety team.### Skills Required* generative AI* Large Language Models (LLMs)* coding agents* data pipelines* automated evaluation* statistical modeling* model activations* chains-of-thought### Tags:UKLondonShare Job:Application planning## What to evaluate before applying### Visa and relocation signals* Visa sponsorship is not explicitly marked on this role.* Relocation support is not explicitly marked.* Primary route to review: Skilled Worker Visa.### Salary and location checks* No salary range is disclosed on this listing.* Location to plan around: London, United Kingdom.* This role is not marked as remote.### Company context* Google has active SoftwareCareers listings in the current job inventory.* Use the company profile and apply link to verify the opening.Google profile### Interview preparation* Experience signal: Minimum qualifications: Bachelor’s degree or equivalent practical experience. 3 years of experience building and shipping technical products. Experience in the domain area of generative AI and Large Language Models (LLMs). Preferred qualifications: Master’s degree or PhD in Engineering, Computer Science, or a related technical field. 3 years of experience developing code, running experiments and analyses collaboratively with coding agents. Experience building large-scale, highly parallelised data pipelines, working on data quality, automated evaluation design and simple statistical modeling. Ability to use AI every day to build and find ways to push the frontier of model capabilities to accelerate work. Ability to approach new research questions and implement technical solutions for them..* Prepare examples for: generative AI, Large Language Models (LLMs), coding agents, data pipelines, automated evaluation.* Compare similar roles before applying.United Kingdom jobsSkilled Worker Visa jobsUnited Kingdom salary guideSalary calculatorRelocation calculatorGoogle sponsorship jobs## Get roles like Research Engineer, Safety Oversight, DeepMindReceive verified AI Safety jobs with visa and relocation signals.## Related JobsMore software jobs in UKD### Research Engineer, Tool Use, DeepMindDeepMind-—London, UKFull-time9DetailsM### Business EngineerMeta-2w agoLondon, UKFull-time23DetailsG### Senior Software Engineer, Full Stack, Google AdsGoogle-2w agoLondon, UKFull-time14DetailsG### Software Engineer III, Full Stack, Publisher InventoryGoogle-2w agoLondon, UKFull-time15DetailsG### Software Engineer III, Site Reliability Engineering, Traffic Network Load BalancingGoogle-2w agoLondon, UKFull-time15Details## Explore related hubsCountry hubUnited Kingdom JobsCompany pageGoogle JobsSalary pageSoftware Engineer SalaryVisa pageSkilled Worker Visa JobsCountry guideUnited Kingdom Relocation GuideCompany directoryVisa Sponsoring CompaniesPrepare to applyATS Resume CheckerDestination compareGermany vs United KingdomDestination compareNetherlands vs United KingdomDatasetVisa Jobs Index## Job application FAQDoes this Research Engineer, Safety Oversight, DeepMind role at Google offer visa sponsorship?: Check the job description and apply link for relocation or sponsorship details for this Google role.How do I apply for Research Engineer, Safety Oversight, DeepMind at Google?: Use the direct apply button on this page to reach the employer application flow without a middleman.Is this Google job verified on SoftwareCareers?: Yes. Listings are manually reviewed for employer authenticity before publication on SoftwareCareers.### Job OverviewJob TitleResearch Engineer, Safety Oversight, DeepMindJob TypeFull-timeCategoryAI SafetyExperienceMinimum qualifications:Bachelor’s degree or equivalent practical experience.3 years of experience building and shipping technical products.Experience in the domain area of generative AI and Large Language Models (LLMs).Preferred qualifications:Master’s degree or PhD in Engineering, Computer Science, or a related technical field.3 years of experience developing code, running experiments and analyses collaboratively with coding agents.Experience building large-scale, highly parallelised data pipelines, working on data quality, automated evaluation design and simple statistical modeling.Ability to use AI every day to build and find ways to push the frontier of model capabilities to accelerate work.Ability to approach new research questions and implement technical solutions for them.LocationLondon, UK